Sharing Experience in Multitask Reinforcement Learning

By Tung-Long Vuong, Do-Van Nguyen, Cong Bui, Hai-Dang Kieu, Viet-Cuong Ta, Quoc-Long Tran, Thanh Ha Le. 2019

22 citations recorded by the source corpus.

In multitask reinforcement learning, tasks often have sub-tasks that share the same solution, even though the overall tasks are different. If the shared-portions could be effectively identified, then the learning process could be improved since all the samples between tasks in the shared space could be used. In this paper, we propose a Sharing Experience Framework (SEF) for simultaneously training of multiple tasks. In SEF, a confidence sharing agent uses task-specific rewards from the environment to identify similar parts that should be shared across tasks and defines those parts as shared-regions between tasks. The shared-regions are expected to guide task-policies sharing their experience during the learning process. The experiments highlight that our framework improves the performance and the stability of learning task-policies, and is possible to help task-policies avoid local optimums.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Yu Zhang
3. Zulfiqar Haider Zaidi
4. Matthew Craig Gombolay
5. Nina M. Moorman
6. Andrew Silva
7. Nakul Gopalan
8. William Silva

In Management Science and Operations Research

1. Qiang Yang
2. Matthew Craig Gombolay
3. Andrew Silva
4. Nakul Gopalan
5. Yu Zhang

Citations in the corpus

• A Survey on Multi-Task Learning (2017, background): “Some works [141], [142], [143], [144], [145], [146], [147], [148], [149], [150] adapt the ideas introduced in Section 2 to MRL.”
• LanCon-Learn: Learning with Language to Enable Generalization in Multi-Task Manipulation (2021, background): “Despite the progress in multi-task learning, much work still centers around defining tasks as an orthonormal space (i.e., tasks are “one-hot” encoded in an orthonormal set [1], [2], [3]).”